Meeting up with Paris ML and SD Deep Learning

Meetups provide an enjoyable, educational atmosphere for Nervana to connect with fellow AI enthusiasts. On April 26th, our cofounder and VP of Algorithms, Arjun Bansal, presented “Nervana and the Future of Computing” at Paris Machine Learning Applications Group’s  Meetup #12 Season 3 highlighting ML Hardware. Paris ML has been commended [...]

By | Wednesday, May 4, 2016|General|

neon v1.4.0 released!

Highlights from this release include:  * VGG16 based Fast R-CNN model using winograd kernels * new, backward compatible, generic data loader * C3D video loader model trained on UCF101 dataset * Deep Dream example * make conv layer printout more informative [#222] * fix some examples to use new arg [...]

By | Friday, April 29, 2016|Product|

Nervana Attends GTC

At this year’s GPU Technology Conference (GTC), deep learning was once again in the spotlight. Several of us from Nervana attended to share knowledge with other experts in the field and learn about new technology. The keynotes and many of the talks given at the conference were focused on the [...]

By | Monday, April 18, 2016|General|

Deep Learning at Scale: Q&A with Naveen Rao, CEO of Nervana

Deep learning has had a major impact in the last three years. Imperfect interactions with machines, such as speech, natural language, or image processing have been made robust by deep learning, which holds promise in finding usable structure in large data sets. Despite this, training processes are lengthy and have proven [...]

By | Wednesday, April 13, 2016|General|

Deep learning, neon, and the Nervana Cloud

On March 3rd, 2016 we held our second SV Deep Learning meetup at Galvanize in San Francisco. Over 150 people attended the sold out event and networked late into the evening. Attendees learned how deep learning techniques can be applied to solve problems in image, video and natural language processing. [...]

By | Wednesday, March 16, 2016|General|

“Not so fast, FFT”: Winograd

Deep learning thrives on speed. Faster training enables the construction of larger and more complex networks to tackle new domains such as speech or decision making. Recently, small convolutional filter sizes have become an important component in convolutional neural networks such as Google’s AlphaGo network or Microsoft’s deep residual networks. [...]

By | Thursday, March 3, 2016|Developer|

Using neon for Scene Recognition: Mini-Places2

Introduction Much of the latest research in computer vision has focused on deep learning techniques. It has been applied to object recognition, where the goal is to predict what type of object is pictured in an image, and object localization, where the goal is to predict an object’s location in [...]

By | Tuesday, February 9, 2016|Developer|